Everything is connected: Graph neural networks

Clinical research text summarization method based on fusion of domain knowledge

OBJECTIVE

The objective of this study is to integrate PICO knowledge into the clinical research text summarization process, aiming to enhance the model's comprehension of biomedical texts while capturing crucial content from the perspective of summary readers, ultimately improving the quality of summaries.

METHODS

We propose a clinical research text summarization method called DKGE-PEGASUS (Domain-Knowledge and Graph Convolutional Enhanced PEGASUS), which is based on integrating domain knowledge. The model mainly consists of three components: a PICO label prediction module, a text information re-mining unit based on Graph Convolutional Neural Networks (GCN), and a pre-trained summarization model. First, the PICO label prediction module is used to identify PICO elements in clinical research texts while obtaining word embeddings enriched with PICO knowledge. Then, we use GCN to reinforce the encoder of the pre-trained summarization model to achieve deeper text information mining while explicitly injecting PICO knowledge. Finally, the outputs of the PICO label prediction module, the GCN text information re-mining unit, and the encoder of the pre-trained model are fused to produce the final coding results, which are then decoded by the decoder to generate summaries.

RESULTS

Experiments conducted on two datasets, PubMed and CDSR, demonstrated the effectiveness of our method. The Rouge-1 scores achieved were 42.64 and 38.57, respectively. Furthermore, the quality of our summarization results was found to significantly outperform the baseline model in comparisons of summarization results for a segment of biomedical text.

CONCLUSION

The method proposed in this paper is better equipped to identify critical elements in clinical research texts and produce a higher-quality summary.

AI-Powered Microfluidics: Shaping the Future of Phenotypic Drug Discovery

Phenotypic drug discovery (PDD), which involves harnessing biological systems directly to uncover effective drugs, has undergone a resurgence in recent years. The rapid advancement of artificial intelligence (AI) over the past few years presents numerous opportunities for augmenting phenotypic drug screening on microfluidic platforms, leveraging its predictive capabilities, data analysis, efficient data processing, etc. Microfluidics coupled with AI is poised to revolutionize the landscape of phenotypic drug discovery. By integrating advanced microfluidic platforms with AI algorithms, researchers can rapidly screen large libraries of compounds, identify novel drug candidates, and elucidate complex biological pathways with unprecedented speed and efficiency. This review provides an overview of recent advances and challenges in AI-based microfluidics and their applications in drug discovery. We discuss the synergistic combination of microfluidic systems for high-throughput screening and AI-driven analysis for phenotype characterization, drug-target interactions, and predictive modeling. In addition, we highlight the potential of AI-powered microfluidics to achieve an automated drug screening system. Overall, AI-powered microfluidics represents a promising approach to shaping the future of phenotypic drug discovery by enabling rapid, cost-effective, and accurate identification of therapeutically relevant compounds.

A multi-view graph contrastive learning framework for deciphering spatially resolved transcriptomics data

Spatially resolved transcriptomics data are being used in a revolutionary way to decipher the spatial pattern of gene expression and the spatial architecture of cell types. Much work has been done to exploit the genomic spatial architectures of cells. Such work is based on the common assumption that gene expression profiles of spatially adjacent spots are more similar than those of more distant spots. However, related work might not consider the nonlocal spatial co-expression dependency, which can better characterize the tissue architectures. Therefore, we propose MuCoST, a Multi-view graph Contrastive learning framework for deciphering complex Spatially resolved Transcriptomic architectures with dual scale structural dependency. To achieve this, we employ spot dependency augmentation by fusing gene expression correlation and spatial location proximity, thereby enabling MuCoST to model both nonlocal spatial co-expression dependency and spatially adjacent dependency. We benchmark MuCoST on four datasets, and we compare it with other state-of-the-art spatial domain identification methods. We demonstrate that MuCoST achieves the highest accuracy on spatial domain identification from various datasets. In particular, MuCoST accurately deciphers subtle biological textures and elaborates the variation of spatially functional patterns.

Improving plant miRNA-target prediction with self-supervised k-mer embedding and spectral graph convolutional neural network

Deciphering the targets of microRNAs (miRNAs) in plants is crucial for comprehending their function and the variation in phenotype that they cause. As the highly cell-specific nature of miRNA regulation, recent computational approaches usually utilize expression data to identify the most physiologically relevant targets. Although these methods are effective, they typically require a large sample size and high-depth sequencing to detect potential miRNA-target pairs, thereby limiting their applicability in improving plant breeding. In this study, we propose a novel miRNA-target prediction framework named kmerPMTF (k-mer-based prediction framework for plant miRNA-target). Our framework effectively extracts the latent semantic embeddings of sequences by utilizing k-mer splitting and a deep self-supervised neural network. We construct multiple similarity networks based on k-mer embeddings and employ graph convolutional networks to derive deep representations of miRNAs and targets and calculate the probabilities of potential associations. We evaluated the performance of kmerPMTF on four typical plant datasets: Arabidopsis thaliana, Oryza sativa, Solanum lycopersicum, and Prunus persica. The results demonstrate its ability to achieve AUPRC values of 84.9%, 91.0%, 80.1%, and 82.1% in 5-fold cross-validation, respectively. Compared with several state-of-the-art existing methods, our framework achieves better performance on threshold-independent evaluation metrics. Overall, our study provides an efficient and simplified methodology for identifying plant miRNA-target associations, which will contribute to a deeper comprehension of miRNA regulatory mechanisms in plants.

Predicting hotspots for disease-causing single nucleotide variants using sequences-based coevolution, network analysis, and machine learning

To enable personalized medicine, it is important yet highly challenging to accurately predict disease-causing mutations in target proteins at high throughput. Previous computational methods have been developed using evolutionary information in combination with various biochemical and structural features of protein residues to discriminate neutral vs. deleterious mutations. However, the power of these methods is often limited because they either assume known protein structures or treat residues independently without fully considering their interactions. To address the above limitations, we build upon recent progress in machine learning, network analysis, and protein language models, and develop a sequences-based variant site prediction workflow based on the protein residue contact networks: 1. We employ and integrate various methods of building protein residue networks using state-of-the-art coevolution analysis tools (RaptorX, DeepMetaPSICOV, and SPOT-Contact) powered by deep learning. 2. We use machine learning algorithms (Random Forest, Gradient Boosting, and Extreme Gradient Boosting) to optimally combine 20 network centrality scores to jointly predict key residues as hot spots for disease mutations. 3. Using a dataset of 107 proteins rich in disease mutations, we rigorously evaluate the network scores individually and collectively (via machine learning). This work supports a promising strategy of combining an ensemble of network scores based on different coevolution analysis methods (and optionally predictive scores from other methods) via machine learning to predict hotspot sites of disease mutations, which will inform downstream applications of disease diagnosis and targeted drug design.

DCGAN-DTA: Predicting drug-target binding affinity with deep convolutional generative adversarial networks

BACKGROUND

In recent years, there has been a growing interest in utilizing computational approaches to predict drug-target binding affinity, aiming to expedite the early drug discovery process. To address the limitations of experimental methods, such as cost and time, several machine learning-based techniques have been developed. However, these methods encounter certain challenges, including the limited availability of training data, reliance on human intervention for feature selection and engineering, and a lack of validation approaches for robust evaluation in real-life applications.

RESULTS

To mitigate these limitations, in this study, we propose a method for drug-target binding affinity prediction based on deep convolutional generative adversarial networks. Additionally, we conducted a series of validation experiments and implemented adversarial control experiments using straw models. These experiments serve to demonstrate the robustness and efficacy of our predictive models. We conducted a comprehensive evaluation of our method by comparing it to baselines and state-of-the-art methods. Two recently updated datasets, namely the BindingDB and PDBBind, were used for this purpose. Our findings indicate that our method outperforms the alternative methods in terms of three performance measures when using warm-start data splitting settings. Moreover, when considering physiochemical-based cold-start data splitting settings, our method demonstrates superior predictive performance, particularly in terms of the concordance index.

CONCLUSION

The results of our study affirm the practical value of our method and its superiority over alternative approaches in predicting drug-target binding affinity across multiple validation sets. This highlights the potential of our approach in accelerating drug repurposing efforts, facilitating novel drug discovery, and ultimately enhancing disease treatment. The data and source code for this study were deposited in the GitHub repository, https://github.com/mojtabaze7/DCGAN-DTA . Furthermore, the web server for our method is accessible at https://dcgan.shinyapps.io/bindingaffinity/ .

GELT: A graph embeddings based lite-transformer for knowledge tracing

The development of intelligent education has led to the emergence of knowledge tracing as a fundamental task in the learning process. Traditionally, the knowledge state of each student has been determined by assessing their performance in previous learning activities. In recent years, Deep Learning approaches have shown promising results in capturing complex representations of human learning activities. However, the interpretability of these models is often compromised due to the end-to-end training strategy they employ. To address this challenge, we draw inspiration from advancements in graph neural networks and propose a novel model called GELT (Graph Embeddings based Lite-Transformer). The purpose of this model is to uncover and understand the relationships between skills and questions. Additionally, we introduce an energy-saving attention mechanism for predicting knowledge states that is both simple and effective. This approach maintains high prediction accuracy while significantly reducing computational costs compared to conventional attention mechanisms. Extensive experimental results demonstrate the superior performance of our proposed model compared to other state-of-the-art baselines on three publicly available real-world datasets for knowledge tracking.

Recurrent neural network for the dynamics of Zika virus spreading

Recurrent Neural Networks (RNNs), a type of machine learning technique, have recently drawn a lot of interest in numerous fields, including epidemiology. Implementing public health interventions in the field of epidemiology depends on efficient modeling and outbreak prediction. Because RNNs can capture sequential dependencies in data, they have become highly effective tools in this field. In this paper, the use of RNNs in epidemic modeling is examined, with a focus on the extent to which they can handle the inherent temporal dynamics in the spread of diseases. The mathematical representation of epidemics requires taking time-dependent variables into account, such as the rate at which infections spread and the long-term effects of interventions. The goal of this study is to use an intelligent computing solution based on RNNs to provide numerical performances and interpretations for the SEIR nonlinear system based on the propagation of the Zika virus (SEIRS-PZV) model. The four patient dynamics, namely susceptible patients S(y), exposed patients admitted in a hospital E(y), the fraction of infective individuals I(y), and recovered patients R(y), are represented by the epidemic version of the nonlinear system, or the SEIR model. SEIRS-PZV is represented by ordinary differential equations (ODEs), which are then solved by the Adams method using the Mathematica software to generate a dataset. The dataset was used as an output for the RNN to train the model and examine results such as regressions, correlations, error histograms, etc. For RNN, we used 100% to train the model with 15 hidden layers and a delay of 2 seconds. The input for the RNN is a time series sequence from 0 to 5, with a step size of 0.05. In the end, we compared the approximated solution with the exact solution by plotting them on the same graph and generating the absolute error plot for each of the 4 cases of SEIRS-PZV. Predictions made by the model appeared to be become more accurate when the mean squared error (MSE) decreased. An increased fit to the observed data was suggested by this decrease in the MSE, which suggested that the variance between the model's predicted values and the actual values was dropping. A minimal absolute error almost equal to zero was obtained, which further supports the usefulness of the suggested strategy. A small absolute error shows the degree to which the model's predictions matches the ground truth values, thus indicating the level of accuracy and precision for the model's output.

Graph-Based Audio Classification Using Pre-Trained Models and Graph Neural Networks

Sound classification plays a crucial role in enhancing the interpretation, analysis, and use of acoustic data, leading to a wide range of practical applications, of which environmental sound analysis is one of the most important. In this paper, we explore the representation of audio data as graphs in the context of sound classification. We propose a methodology that leverages pre-trained audio models to extract deep features from audio files, which are then employed as node information to build graphs. Subsequently, we train various graph neural networks (GNNs), specifically graph convolutional networks (GCNs), GraphSAGE, and graph attention networks (GATs), to solve multi-class audio classification problems. Our findings underscore the effectiveness of employing graphs to represent audio data. Moreover, they highlight the competitive performance of GNNs in sound classification endeavors, with the GAT model emerging as the top performer, achieving a mean accuracy of 83% in classifying environmental sounds and 91% in identifying the land cover of a site based on its audio recording. In conclusion, this study provides novel insights into the potential of graph representation learning techniques for analyzing audio data.

TacticAI: an AI assistant for football tactics

Identifying key patterns of tactics implemented by rival teams, and developing effective responses, lies at the heart of modern football. However, doing so algorithmically remains an open research challenge. To address this unmet need, we propose TacticAI, an AI football tactics assistant developed and evaluated in close collaboration with domain experts from Liverpool FC. We focus on analysing corner kicks, as they offer coaches the most direct opportunities for interventions and improvements. TacticAI incorporates both a predictive and a generative component, allowing the coaches to effectively sample and explore alternative player setups for each corner kick routine and to select those with the highest predicted likelihood of success. We validate TacticAI on a number of relevant benchmark tasks: predicting receivers and shot attempts and recommending player position adjustments. The utility of TacticAI is validated by a qualitative study conducted with football domain experts at Liverpool FC. We show that TacticAI's model suggestions are not only indistinguishable from real tactics, but also favoured over existing tactics 90% of the time, and that TacticAI offers an effective corner kick retrieval system. TacticAI achieves these results despite the limited availability of gold-standard data, achieving data efficiency through geometric deep learning.

Prediction of bitterness based on modular designed graph neural network

Motivation

Bitterness plays a pivotal role in our ability to identify and evade harmful substances in food. As one of the five tastes, it constitutes a critical component of our sensory experiences. However, the reliance on human tasting for discerning flavors presents cost challenges, rendering in silico prediction of bitterness a more practical alternative.

Results

In this study, we introduce the use of Graph Neural Networks (GNNs) in bitterness prediction, superseding traditional machine learning techniques. We developed an advanced model, a Hybrid Graph Neural Network (HGNN), surpassing conventional GNNs according to tests on public datasets. Using HGNN and three other GNNs, we designed BitterGNNs, a bitterness predictor that achieved an AUC value of 0.87 in both external bitter/non-bitter and bitter/sweet evaluations, outperforming the acclaimed RDKFP-MLP predictor with AUC values of 0.86 and 0.85. We further created a bitterness prediction website and database, TastePD (https://www.tastepd.com/). The BitterGNNs predictor, built on GNNs, offers accurate bitterness predictions, enhancing the efficacy of bitterness prediction, aiding advanced food testing methodology development, and deepening our understanding of bitterness origins.

Availability and implementation

TastePD can be available at https://www.tastepd.com, all codes are at https://github.com/heyigacu/BitterGNN.

Mixtures Recomposition by Neural Nets: A Multidisciplinary Overview

Artificial Neural Networks (ANNs) are transforming how we understand chemical mixtures, providing an expressive view of the chemical space and multiscale processes. Their hybridization with physical knowledge can bridge the gap between predictivity and understanding of the underlying processes. This overview explores recent progress in ANNs, particularly their potential in the 'recomposition' of chemical mixtures. Graph-based representations reveal patterns among mixture components, and deep learning models excel in capturing complexity and symmetries when compared to traditional Quantitative Structure-Property Relationship models. Key components, such as Hamiltonian networks and convolution operations, play a central role in representing multiscale mixtures. The integration of ANNs with Chemical Reaction Networks and Physics-Informed Neural Networks for inverse chemical kinetic problems is also examined. The combination of sensors with ANNs shows promise in optical and biomimetic applications. A common ground is identified in the context of statistical physics, where ANN-based methods iteratively adapt their models by blending their initial states with training data. The concept of mixture recomposition unveils a reciprocal inspiration between ANNs and reactive mixtures, highlighting learning behaviors influenced by the training environment.

Relative molecule self-attention transformer

The prediction of molecular properties is a crucial aspect in drug discovery that can save a lot of money and time during the drug design process. The use of machine learning methods to predict molecular properties has become increasingly popular in recent years. Despite advancements in the field, several challenges remain that need to be addressed, like finding an optimal pre-training procedure to improve performance on small datasets, which are common in drug discovery. In our paper, we tackle these problems by introducing Relative Molecule Self-Attention Transformer for molecular representation learning. It is a novel architecture that uses relative self-attention and 3D molecular representation to capture the interactions between atoms and bonds that enrich the backbone model with domain-specific inductive biases. Furthermore, our two-step pretraining procedure allows us to tune only a few hyperparameter values to achieve good performance comparable with state-of-the-art models on a wide selection of downstream tasks.

Neuroscience Needs Network Science

The brain is a complex system comprising a myriad of interacting neurons, posing significant challenges in understanding its structure, function, and dynamics. Network science has emerged as a powerful tool for studying such interconnected systems, offering a framework for integrating multiscale data and complexity. To date, network methods have significantly advanced functional imaging studies of the human brain and have facilitated the development of control theory-based applications for directing brain activity. Here, we discuss emerging frontiers for network neuroscience in the brain atlas era, addressing the challenges and opportunities in integrating multiple data streams for understanding the neural transitions from development to healthy function to disease. We underscore the importance of fostering interdisciplinary opportunities through workshops, conferences, and funding initiatives, such as supporting students and postdoctoral fellows with interests in both disciplines. By bringing together the network science and neuroscience communities, we can develop novel network-based methods tailored to neural circuits, paving the way toward a deeper understanding of the brain and its functions, as well as offering new challenges for network science.

Graph-based clinical recommender: Predicting specialists procedure orders using graph representation learning

OBJECTIVE

To determine whether graph neural network based models of electronic health records can predict specialty consultation care needs for endocrinology and hematology more accurately than the standard of care checklists and other conventional medical recommendation algorithms in the literature.

METHODS

Demand for medical expertise far outstrips supply, with tens of millions in the US alone with deficient access to specialty care. Rather than potentially months long delays to initiate diagnostic workup and medical treatment with a specialist, referring primary care supported by an automated recommender algorithm could anticipate and directly initiate patient evaluation that would otherwise be needed at subsequent a specialist appointment. We propose a novel graph representation learning approach with a heterogeneous graph neural network to model structured electronic health records and formulate recommendation/prediction of subsequent specialist orders as a link prediction problem.

RESULTS

Models are trained and assessed in two specialty care sites: endocrinology and hematology. Our experimental results show that our model achieves an 8% improvement in ROC-AUC for endocrinology (ROC-AUC = 0.88) and 5% improvement for hematology (ROC-AUC = 0.84) personalized procedure recommendations over prior medical recommender systems. These recommender algorithm approaches provide medical procedure recommendations for endocrinology referrals more effectively than manual clinical checklists (recommender: precision = 0.60, recall = 0.27, F1-score = 0.37) vs. (checklist: precision = 0.16, recall = 0.28, F1-score = 0.20), and similarly for hematology referrals (recommender: precision = 0.44, recall = 0.38, F1-score = 0.41) vs. (checklist: precision = 0.27, recall = 0.71, F1-score = 0.39).

CONCLUSION

Embedding graph neural network models into clinical care can improve digital specialty consultation systems and expand the access to medical experience of prior similar cases.

BioGraph: Data Model for Linking and Querying Diverse Biological Metadata

Studying the association of gene function, diseases, and regulatory gene network reconstruction demands data compatibility. Data from different databases follow distinct schemas and are accessible in heterogenic ways. Although the experiments differ, data may still be related to the same biological entities. Some entities may not be strictly biological, such as geolocations of habitats or paper references, but they provide a broader context for other entities. The same entities from different datasets can share similar properties, which may or may not be found within other datasets. Joint, simultaneous data fetching from multiple data sources is complicated for the end-user or, in many cases, unsupported and inefficient due to differences in data structures and ways of accessing the data. We propose BioGraph-a new model that enables connecting and retrieving information from the linked biological data that originated from diverse datasets. We have tested the model on metadata collected from five diverse public datasets and successfully constructed a knowledge graph containing more than 17 million model objects, of which 2.5 million are individual biological entity objects. The model enables the selection of complex patterns and retrieval of matched results that can be discovered only by joining the data from multiple sources.